Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 13730
    Prev
    Next
    INDEX
    Explanations

    introductions or continuations of text sections

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.02
    2:0.19
    3:0.07
    4:0.12
    5:0.10
    6:0.08
    7:0.03
    8:0.08
    9:0.07
    10:0.07
    11:0.03
    Negative Logits
     Deliver
    -1.09
     Ventura
    -1.09
     CV
    -1.06
     Harley
    -1.06
     Reilly
    -1.06
     Late
    -1.01
     suspension
    -1.00
     charge
    -1.00
     martial
    -0.99
    SourceFile
    -0.98
    POSITIVE LOGITS
    _>
    1.45
     importantly
    1.38
    hesda
    1.31
    anwhile
    1.21
     GOODMAN
    1.21
    ividual
    1.18
     conclud
    1.18
    ritical
    1.17
    henko
    1.16
     coerc
    1.15
    Activations Density 0.048%

    No Known Activations